public class SparseSampling.StateNode
extends java.lang.Object
Constructor and Description |
---|
SparseSampling.StateNode(StateHashTuple sh,
int height)
Creates a node for the given hased state at the given height
|
Modifier and Type | Method and Description |
---|---|
java.util.List<QValue> |
estimateQs()
Estimates and returns the Q-values for this node.
|
double |
estimateV()
Returns the estimated Q-value if this node is closed, or estimates it and closes it otherwise.
|
protected double |
fullBelmmanQValue(GroundedAction ga)
Computes the exact Q-value using full Bellman update with the actual transition dynamics.
|
protected double |
sampledBellmanQEstimate(GroundedAction ga)
Estimates the Q-value using sampling from the transition dynamics.
|
public SparseSampling.StateNode(StateHashTuple sh, int height)
sh
- the hashed stateheight
- the height of the nodepublic java.util.List<QValue> estimateQs()
List
of the estiamted Q-values for each action.protected double sampledBellmanQEstimate(GroundedAction ga)
ga
- the action for which the Q-value estimate is to be returnedprotected double fullBelmmanQValue(GroundedAction ga)
ga
- the action for which the Q-value estimate is to be returnedpublic double estimateV()